Jover Lee joverlee521

In walking through git subrepo pull with @j23414 for nextstrain/mpox#182, we ran into unexpected merge conflicts.

$ git subrepo pull ingest/vendored -dv
>>> git rev-parse --verify HEAD
* Assert that working copy is clean: /Users/jlee2346/Repos/nextstrain/monkeypox
* Check for worktree with branch subrepo/ingest/vendored
  * Fetch the upstream: https://github.com/nextstrain/ingest (main).
>>> git fetch --no-tags --quiet https://github.com/nextstrain/ingest main

Example data (test-data.tsv)

ID	city	latitude	longitude	lineage	lineage__color
AAA	Auckland	-37	174	B.1.1	#F020E2
BBB	Auckland	-39	175	C.12	#20C9F0
CCC	Wellington	-41	174	C.12	#20C9F0

Example commands

a colours TSV mapping lineage -> hex. (Including some form of colour averaging if there are multiple hexes per lineage, which happens.)

	"""
	Workflow for tracking down records with mismatched lineages from the ingest
	workflow compared to the metadata from fauna.

	Intended to be run once to create the annotations.tsv for the ingest workflow
	to correct the lineages using the version of files on S3 from 2025-06-13.
	"""
	SUBTYPES = [
	"h1n1pdm",
	"h3n2",

	#!vd -p
	{"sheet": "global", "col": null, "row": "header", "longname": "set-option", "input": "0", "keystrokes": "", "comment": null, "replayable": null}
	{"longname": "open-file", "input": "augur/data/geolocation_rules.tsv", "keystrokes": "o", "replayable": true}
	{"sheet": "geolocation_rules", "col": 1, "row": "", "longname": "addcol-split", "input": "/", "keystrokes": ":", "comment": "add column split by regex", "replayable": true}
	{"sheet": "geolocation_rules", "col": "_re", "row": "", "longname": "expand-col", "input": "", "keystrokes": "(", "comment": "expand current column of containers one level", "replayable": true}
	{"sheet": "geolocation_rules", "col": "_re[1]", "row": "", "longname": "key-col", "input": "", "keystrokes": "!", "comment": "toggle current column as a key column", "replayable": true}
	{"sheet": "geolocation_rules", "col": 1, "row": "", "longname": "key-col", "input": "", "keystrokes": "!", "comment": "toggle current column as a key column", "replayable": true}
	{"sheet": "geolocation_rules"


	PREVIEW = config.get("preview", False)
	YEAR = config.get("year", '2024')

	VIDRL_PATH = "../fludata/VIDRL-Melbourne-WHO-CC/raw-data"

	H1N1_PATH = f"{VIDRL_PATH}/A/H1N1pdm/HI"
	H3N2_PATH = f"{VIDRL_PATH}/A/H3N2/HI"
	H3N2_FRA = f"{VIDRL_PATH}/A/H3N2/FRA"
	VIC_PATH = f"{VIDRL_PATH}/B/Victoria/HI"

	subtypes = ['h1n1pdm']
	segments = ['ha', 'na']
	times = ['pandemic']

	rule all:
	input:
	expand("data/{subtype}/{segment}/{time}.done", subtype=subtypes, segment=segments, time=times)

	rule copy_aws_files:
	output: touch("data/{subtype}/{segment}/{time}.done")

	<!doctype html>

	<html lang="en">

	<head>
	<meta charset="utf-8">
	<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
	<meta name="description" content="">
	<meta name="author" content="">
	<title>Snakemake Report</title>

	subtypes = ['h3n2', 'h1n1pdm', 'vic', 'yam']
	segments = ['ha', 'na']
	times = ['12y', '6y', '3y', '2y', '6m']

	rule all:
	input:
	expand("data/{subtype}/{segment}/{time}.done", subtype=subtypes, segment=segments, time=times)

	rule copy_aws_files:
	output: touch("data/{subtype}/{segment}/{time}.done")

	#!/bin/bash

	bucket="nextstrain-data"
	s3_prefix="files/workflows/forecasts-ncov"

	s3_trial_prefix="trial/seq-counts-workflow"

	data_provenances=("open" "gisaid")
	variants=("nextstrain_clades" "pango_lineages")
	georesolutions=("global" "usa")

	rule all:
	input: "data/rule_all.txt"

	rule a:
	output: touch("data/rule_a.txt")


	rule b:
	input: "data/rule_a.txt"
	output: "data/rule_a_hardlink.txt"